© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 78116
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /**↵
    -0.07
    未知
    -0.07
    >Error
    -0.07
    Fmt
    -0.06
    glyphicon
    -0.06
    undreds
    -0.06
    字
    -0.06
    符合条件
    -0.06
    П
    -0.06
    >User
    -0.06
    POSITIVE LOGITS
    _MI
    0.07
     pprint
    0.07
     AAP
    0.07
     insane
    0.07
    ぇ
    0.07
     llama
    0.07
    調べ
    0.07
    롓
    0.07
     javascript
    0.07
    绫
    0.07
    Activations Density 0.004%

    No Known Activations